Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/leoyang183/sync-agents-settings/agents-mdgit clone --depth 1 https://github.com/Leoyang183/sync-agents-settingsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/leoyang183/sync-agents-settings/agents-md)<a href="https://agentmods.dev/instructions/leoyang183/sync-agents-settings/agents-md"><img src="https://agentmods.dev/badge/instructions/leoyang183/sync-agents-settings/agents-md.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00615 | $0.00615 |
| Opus 5 | $0.00308 | $0.00308 |
| Sonnet 5 | $0.00123 | $0.00123 |
| Haiku 4.5 | $0.00061 | $0.00061 |
Grade A, and why
sync-agents-settings AGENTS.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Guidelines
Project Structure & Module Organization
- Core source lives in
src/. - CLI entrypoint:
src/cli.ts. - MCP sync logic is split by concern:
- readers:
src/reader.ts - writers:
src/writers/*.ts(target-specific adapters) - validation/health:
src/validation.ts,src/doctor.ts,src/reconcile.ts,src/fix.ts - instruction sync:
src/instructions.ts
- readers:
- Tests are in
src/__tests__/(unit + workflow-level tests). - User docs live in
README.mdand localized variants underdocs/i18n/. - Command docs for Claude plugin are in
commands/.
Build, Test, and Development Commands
pnpm dev <command>: run CLI from source (example:pnpm dev sync -- --dry-run).pnpm build: compile TypeScript todist/.pnpm test: run full Vitest suite.pnpm lint: run ESLint onsrc/.pnpm format/pnpm format:check: format or verify formatting../ci-local.sh: quick local CI-style check.
Coding Style & Naming Conventions
- Language: TypeScript (ESM).
- Indentation: 2 spaces; keep files UTF-8 and newline-terminated.
- Prefer small, single-purpose modules and explicit types for public functions.
- Naming:
- files: kebab/lowercase (
report-parser.ts,claude-format.ts) - functions/variables:
camelCase - types/interfaces:
PascalCase
- files: kebab/lowercase (
- Follow existing formatter/linter behavior (
prettier,eslint).
Testing Guidelines
- Framework: Vitest (
vitest.config.ts). - Add/adjust tests in
src/__tests__/for every behavior change. - Test names should describe behavior (e.g.,
it("skips existing servers")). - Run focused tests during development:
pnpm vitest run src/__tests__/foo.test.ts. - Keep deterministic tests; avoid network/runtime dependencies.
Commit & Pull Request Guidelines
- Follow Conventional Commits as used in history:
feat:,fix:,docs:,test:,chore:. - Keep commits scoped and atomic (code + tests + docs for that change).
- PRs should include:
- what changed and why
- affected commands/targets (e.g.,
gemini,codex,kimi,qwen,amp,cline,windsurf) - verification steps and command outputs
- linked issue (if applicable)
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 3d ago First seen · 53 lines · 615 tokens per session scan A d52fd9a6fe82
sync-agents-settings AGENTS.md is an instructions file published in the GitHub repository Leoyang183/sync-agents-settings (8 stars, last pushed 5mo ago), licensed MIT. It adds 615 tokens to every session, about $0.0031 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
TokenTracker CLAUDE.md
Claude Code instructions for xiufengsun/TokenTracker, covering claude.md, project shape, frequently used commands, what's where and load-bearing conventions.
TokenTracker AGENTS.md
AGENTS.md instructions for xiufengsun/TokenTracker, covering agent instructions and insforge backend.
turnbreak AGENTS.md
Instructions for Milkeles/turnbreak, covering agent instructions file: turnbreak, 1. project overview, 2. commands, 3. code style and 4. repository conventions.
IDE-Adapter CLAUDE.md
Instructions for godstale/IDE-Adapter, covering claude.md, commands, architecture, adding a new handler and protocol rules.
IDE-Adapter GEMINI.md
Instructions for godstale/IDE-Adapter, covering gemini.md, project overview, building and running and development conventions.
agent-recall CLAUDE.md
Claude Code instructions for d-wwei/agent-recall, covering agent recall: ai development instructions, architecture, privacy tags, build commands and configuration.